{"total":53,"rows":[{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2110.07143","title":"bert2BERT: Towards Reusable Pretrained Language Models","created":"2021-10-14","cited_by_count":70,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"area":null},{"id":"2102.08574","title":"Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks","created":"2021-02-17","cited_by_count":49,"area":null},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49,"area":null},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41,"area":null},{"id":"2211.15188","title":"Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2106.09563","title":"On Anytime Learning at Macroscale","created":"2021-06-17","cited_by_count":20,"area":null},{"id":"2109.14536","title":"PINNup: Robust neural network wavefield solutions using frequency upscaling and neuron splitting","created":"2021-09-29","cited_by_count":20,"area":null},{"id":"2202.08539","title":"When, where, and how to add new neurons to ANNs","created":"2022-02-17","cited_by_count":18,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2307.04526","title":"Self-Expanding Neural Networks","created":"2023-07-10","cited_by_count":14,"area":null},{"id":"2207.09663","title":"Streamable Neural Fields","created":"2022-07-20","cited_by_count":13,"area":null},{"id":"2505.05587","title":"Steepest Descent Density Control for Compact 3D Gaussian Splatting","created":"2025-05-08","cited_by_count":13,"area":null},{"id":"2401.09192","title":"Preparing Lessons for Progressive Training on Language Models","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2306.12700","title":"Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2311.04251","title":"MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2406.06567","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","created":"2024-06-03","cited_by_count":7,"area":null},{"id":"2402.05626","title":"Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding","created":"2024-02-08","cited_by_count":6,"area":null},{"id":"2410.01779","title":"Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2102.07071","title":"Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2312.09148","title":"Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2501.15889","title":"Adaptive Width Neural Networks","created":"2025-01-27","cited_by_count":4,"area":null},{"id":"2401.03104","title":"When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks","created":"2024-01-06","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2506.14951","title":"Flat Channels to Infinity in Neural Loss Landscapes","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2211.06860","title":"An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecture","created":"2022-11-13","cited_by_count":2,"area":null},{"id":"2502.06885","title":"Topological derivative approach for deep neural network architecture adaptation","created":"2025-02-08","cited_by_count":2,"area":null},{"id":"2106.07211","title":"Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2311.15995","title":"SensLI: Sensitivity-Based Layer Insertion for Neural Networks","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2411.05855","title":"Learning Morphisms with Gauss-Newton Approximation for Growing Networks","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2507.02466","title":"Variational Kolmogorov-Arnold Network","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.19151","title":"Saddle Hierarchy in Dense Associative Memory","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.18842","title":"Shared-Weights Extender and Gradient Voting for Neural Network Expansion","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2602.08723","title":"Data Reconstruction: Identifiability and Optimization with Sample Splitting","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2110.08857","title":"Growing Representation Learning","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2201.06500","title":"Growing Neural Network with Shared Parameter","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2309.08615","title":"Energy Concerns with HPC Systems and Applications","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2402.12418","title":"Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2408.13291","title":"Growing Deep Neural Network Considering with Similarity between Neurons","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2410.07691","title":"Growing Efficient Accurate and Robust Neural Networks on the Edge","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2603.19759","title":"Growing Networks with Autonomous Pruning","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.15435","title":"On the Stability of Growth in Structural Plasticity: Forward-Active yet Backward-Starved","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.31110","title":"Explaining Machine Learning and Memorization with Statistical Mechanics","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.07637","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.14664","title":"Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.33880","title":"Neuron-Level Architecture Growth: A Controlled Evaluation for EEG Time-Series Decoding","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.00180","title":"Four Ways to Grow a Classifier and Why One of Them Cannot Learn","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.16147","title":"BARTER: Compact Dynamic Sparse Training with Standard Dense Kernels","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}